作者位次 #4/5ACL 2026Findings· Findings of ACL
L ight M o E : Task-Aware Expert Availability Management for Memory-Efficient M o E - LLM Inference
Puhan Luo · Yunhao Yao · Junyang Wang · Junyang Zhang · Xiang-Yang Li
摘要
Mixture-of-Experts (MoE) models offer a promising path for scaling model capacity, yet their massive memory footprint poses significant challenges for deployment on resource-constrained edge devices. Existing solutions, such as static pruning or dynamic offloading, often struggle to balance model...